agentleFS
toneron2toneron2/agentic-platform/.claude/skills/prime/SKILL.md

prime

Skill2 starsChanged 10 months agoMITView on GitHub

Inject context at session start

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run bd prime for Beads context

    line 18
  2. Distinctive:

    Check inbox for pending items

    line 20
  3. Distinctive:

    Session start: Always (via conductor)

    line 102
  4. Distinctive:

    After long idle: If session > 30 min without activity

    line 103

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Prime Skill - Context Injection

You are the context primer for the agentic platform. Your role is to efficiently load relevant context at session start without overwhelming the token budget.

Core Function

At session start:

  1. Run bd prime for Beads context
  2. Scan brain/ for recent activity
  3. Check inbox for pending items
  4. Load last session state
  5. Return condensed context

Priming Process

Step 1: Beads Prime

bd prime

This returns ~1-2k tokens of:

  • Ready work (unblocked tasks)
  • Blocked items (what's blocking)
  • Recent activity
  • Key dependencies

Step 2: Brain Scan (Lightweight)

# Recent activity (last 3 days)
find brain/ -type f -mtime -3 -name "*.md" | head -10

# Inbox count
ls brain/inbox/*.md 2>/dev/null | wc -l

# Due soon (admin)
grep -l "due_date:" brain/admin/*.md 2>/dev/null | head -5

Step 3: Load Session State

cat state/session.json 2>/dev/null
cat state/last-digest.json 2>/dev/null

Step 4: Compile Context

Return a condensed summary:

## Session Context

**Beads State:**
- Ready: N tasks
- Blocked: N tasks
- Recent: [last 3 activities]

**Brain Activity:**
- Recent files: [list of 5 most recent]
- Inbox pending: N items
- Due soon: [items due in 3 days]

**Last Session:**
- Date: [timestamp]
- Captures: N
- Tasks completed: N

**Digest Status:**
- Last digest: [timestamp]
- Last review: [timestamp]

Token Budget

Target: ~500-1000 tokens total

Prioritize:

  1. Ready tasks (most actionable)
  2. Overdue items (urgent)
  3. Recent brain activity (continuity)
  4. Session state (context)

Truncate if necessary:

  • Max 5 ready tasks shown
  • Max 5 recent files
  • Max 3 due items

When to Prime

  • Session start: Always (via conductor)
  • After long idle: If session > 30 min without activity
  • Before compaction: Preserve critical context

Example Output

## Session Context

**Beads State:**
- Ready: 5 tasks
- Blocked: 2 tasks
- Recent: [bd-a3f8] closed 2h ago

**Top Ready:**
1. [bd-b2c1] Review PR #42 (P1)
2. [bd-c3d2] Update docs (P2)
3. [bd-d4e3] Fix login bug (P2)

**Brain Activity:**
- brain/people/tom.md (modified 1h ago)
- brain/projects/api-refactor.md (modified 3h ago)
- Inbox: 2 items pending

**Due Soon:**
- Renew car registration (tomorrow)
- Quarterly report (3 days)

**Last Session:**
- 6 hours ago
- 3 captures, 1 task completed

Ready to work. What's your focus?

Error Handling

ErrorAction
Beads not initializedNote it, skip beads context
brain/ emptyNote it, suggest first capture
state/ missingInitialize fresh session state
bd command failsContinue with brain-only context

Integration

Called by:

  • Conductor skill at session start
  • Automatically before context compaction events

Download now (ZIP)

  • Other versions9 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use research.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • NVIDIASkill

      research

      Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

      Also in 3 projects that use this

  • In this repository6 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.